AIYIYA/my_aa

This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.7596
• Validation Loss: 1.4913
• Train Accuracy: 0.6753
• Epoch: 29

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 280, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
3.4316	3.2876	0.2078	0
3.0452	3.0083	0.2338	1
2.6954	2.7106	0.3766	2
2.3815	2.4910	0.4935	3
2.0499	2.3035	0.5584	4
1.8322	2.1419	0.5844	5
1.6292	1.9997	0.6104	6
1.4675	1.8933	0.6234	7
1.3115	1.8016	0.5974	8
1.2088	1.7273	0.6364	9
1.1053	1.6728	0.6623	10
1.0254	1.6284	0.6364	11
0.9600	1.6252	0.6494	12
0.9058	1.5662	0.6623	13
0.8675	1.5423	0.6623	14
0.8434	1.5208	0.6753	15
0.8356	1.5140	0.6753	16
0.8070	1.5024	0.6753	17
0.7749	1.4941	0.6753	18
0.7805	1.4913	0.6753	19
0.7764	1.4913	0.6753	20
0.7630	1.4913	0.6753	21
0.7806	1.4913	0.6753	22
0.7665	1.4913	0.6753	23
0.7803	1.4913	0.6753	24
0.7778	1.4913	0.6753	25
0.7781	1.4913	0.6753	26
0.7798	1.4913	0.6753	27
0.7845	1.4913	0.6753	28
0.7596	1.4913	0.6753	29

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3